Micro-DualNet: Dual-Path Spatio–Temporal Network for Micro-Action Recognition
Year: 2026
Type: conference-paper
Abstract: Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one’s head or tapping fingers. Such subtle actions are essential for social communication, ubiquitously used in natural interactions, and thus critical for fine-grained video understanding, yet remain poorly understood by current computer vision systems. We identify a fundamental challenge: micro-actions exhibit diverse spatio-temporal characteristics where some are defined by spatial configurations (e.g., “covering face”) while others manifest through temporal dynamics (e.g., “leg shaking"). Existing methods that commit to a single spatio-temporal decomposition cannot accommodate this diversity. We propose Micro-DualNet, a dual-path network that processes anatomically-grounded spatial entities through parallel Spatial-Temporal (ST) and Temporal-Spatial (TS) pathways. The ST path captures spatial configurations before modeling temporal dynamics, while the TS path inverts this order to prioritize temporal dynamics. Rather than fixed fusion, we introduce entity-level adaptive routing where each body part learns its optimal processing preference, complemented by Mutual Action Consistency (MAC) loss that enforces crosspath coherence. Extensive experiments demonstrate competitive performance on MA-52 dataset (65.10% Top-1, 68.72% F1 ${ }_{\text {mean }}$) and state-of-the-art results on iMiGUE ($76.88 \%$ Top-1) dataset. Ablations confirm that position-based actions benefit from ST processing while motion-based actions favor TS processing, validating that micro-actions require flexible complementary decomposition. Our work reveals that architectural adaptation to the inherent complexity of micro-actions is essential for advancing fine-grained video understanding. Clinical validation on an in-house dataset of 290 individuals demonstrates that Micro-DualNet-detected micro-actions reveal statistically significant behavioral differences between kids with autism spectrum disorder, other psychiatric conditions, or typical development, suggesting potential for automated behavioral assessment.
Institution: Children's Hospital of Philadelphia
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7165004250